User | M91 |
Upload Date | July 25 2025 12:20 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 26.0 |
Model | iPhone 16 Pro Max |
Model ID | iPhone17,2 |
Motherboard | D94AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.44 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1984
368.9 IPS |
|
Image Classification (HP)
|
100% |
14098
2.62 KIPS |
|
Image Classification (Q)
|
97% |
18487
3.45 KIPS |
|
Image Segmentation (SP)
|
100% |
1774
28.8 IPS |
|
Image Segmentation (HP)
|
100% |
18144
294.1 IPS |
|
Image Segmentation (Q)
|
99% |
23677
383.8 IPS |
|
Pose Estimation (SP)
|
100% |
8568
10.00 IPS |
|
Pose Estimation (HP)
|
100% |
145657
170.0 IPS |
|
Pose Estimation (Q)
|
95% |
287546
337.0 IPS |
|
Object Detection (SP)
|
100% |
2294
181.9 IPS |
|
Object Detection (HP)
|
100% |
15732
1.25 KIPS |
|
Object Detection (Q)
|
91% |
21031
1.68 KIPS |
|
Face Detection (SP)
|
100% |
3613
42.9 IPS |
|
Face Detection (HP)
|
100% |
39439
468.6 IPS |
|
Face Detection (Q)
|
100% |
53339
633.8 IPS |
|
Depth Estimation (SP)
|
100% |
7845
60.4 IPS |
|
Depth Estimation (HP)
|
99% |
93642
721.5 IPS |
|
Depth Estimation (Q)
|
85% |
160050
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
20877
26.8 IPS |
|
Style Transfer (HP)
|
100% |
243700
313.3 IPS |
|
Style Transfer (Q)
|
96% |
293562
378.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5222
192.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
50258
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
76672
2.83 KIPS |
|
Text Classification (SP)
|
100% |
3746
5.00 KIPS |
|
Text Classification (HP)
|
99% |
6118
8.17 KIPS |
|
Text Classification (Q)
|
93% |
6231
8.36 KIPS |
|
Machine Translation (SP)
|
100% |
4038
69.6 IPS |
|
Machine Translation (HP)
|
100% |
10975
189.1 IPS |
|
Machine Translation (Q)
|
98% |
12506
216.1 IPS |